proton_reply_email · Proton MCP Server MCP: Risk & Policy

WHAT IT DOES

What proton_reply_email does on Proton MCP Server

AI agents use proton_reply_email to create or update resources in Proton MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Proton MCP Server environment.

WHY IT NEEDS A POLICY

Why proton_reply_email needs a policy

Sending emails is a Write operation—it creates new, reversible data (emails can be deleted or recalled). However, severity is high because an AI agent with uncontrolled access could send emails to unintended recipients, disclose sensitive information, or impersonate the user in email conversations, causing reputational or information security harm. The ability to 'reply to all' multiplies the blast radius.

From the tool's definition Tool name is 'proton_reply_email' and description states it 'Send[s] a reply to an existing email' with ability to 'reply to all or just the sender.' This is a composing and sending action that creates new email messages.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

proton_reply_email Rate-limited

proton_reply_email stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "proton_reply_email": {
      "limits": [
        {
          "counter": "proton_reply_email_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Proton MCP Server, so you can run agents against it safely.

FAQ

Questions about proton_reply_email

What does the proton_reply_email tool do? +

Send a reply to an existing email. Properly sets In-Reply-To and References headers for threading. Can reply to all or just the sender. It is categorised as a Write tool in the Proton MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on proton_reply_email? +

Register the Proton MCP Server MCP server in PolicyLayer and add a rule for proton_reply_email: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Proton MCP Server. Nothing to install.

What risk level is proton_reply_email? +

proton_reply_email is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit proton_reply_email? +

Yes. Add a rate_limit block to the proton_reply_email rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block proton_reply_email completely? +

Set action: deny in the PolicyLayer policy for proton_reply_email. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides proton_reply_email? +

proton_reply_email is provided by the Proton MCP Server MCP server (sugar-crash-studios/proton-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.